Publications
Marjieh, R.*, Kumar, S.*, Campbell, D., Zhang , L., Bencomo, G., Snell, J., Griffiths, T.L. Using Contrastive Learning with Generative Similarity to Learn Spaces that Capture Human Inductive Biases. arXiv. (Under Review)
Kumar, S.*, Sumers, T. R.*, Yamakoshi, T., Goldstein, A., Hasson, U., Norman, K. A., Griffiths, T.L., Hawkins, R.D., Nastase, S. A. (2022). Shared functional specialization in transformer-based language models and the human brain. bioRxiv. Nature Communications (In Press)
Kumar, S.*, Marjieh, R.*, Zhang, B., Campbell, D., Hu, M. Y., Bhatt, U., Lake, B., & Griffiths, T. L. (2024). Comparing Abstraction in Humans and Large Language Models Using Multimodal Serial Reproduction. arXiv In Proceedings of the 46th Annual Meeting of the Cognitive Science Society} [Oral Presentation, Top 20% out of ~1200 submissions]
Velazquez-Vargas, C. A., Christian, I. R., Taylor, J. A., & Kumar, S. (2024). Learning to Abstract Visuomotor Mappings using Meta-Reinforcement Learning. arXiv In Proceedings of the 46th Annual Meeting of the Cognitive Science Society
Campbell, D.*, Kumar, S.*, Giallanza, T., Griffiths, T. L., & Cohen, J. D. (2024). Human-Like Geometric Abstraction in Large Pre-trained Neural Networks. arXiv In Proceedings of the 46th Annual Meeting of the Cognitive Science Society
Griffiths, T. L., Kumar, S., & McCoy, R. T. (2023). On the hazards of relating representations and inductive biases. Behavioral and Brain Sciences, 46, e275.
Kumar, S., Dasgupta, I., Daw, N. D., Cohen, J. D., & Griffiths, T. L. (2023). Disentangling abstraction from statistical pattern matching in human and machine learning. PLoS computational biology, 19(8), e1011316.
Kumar, S., Correa, C. G., Dasgupta, I., Marjieh, R., Hu, M. Y., Hawkins, R. D., Daw, N.D., Cohen, J.D., Narasimhan, K., & Griffiths, T. L. (2022). Using Natural Language and Program Abstractions to Instill Human Inductive Biases in Machines In Proceedings of the 36th Conference on Neural Information Processing Systems (NeurIPS) 2022. arXiv [Outstanding Paper Award, Top 13/10K+ submissions]
Kumar, S., Dasgupta, I., Cohen, J. D., Daw, N. D., & Griffiths, T. L. (2021). Meta-Learning of Structured Task Distributions in Humans and Machines. In Proceedings of the 9th International Conference on Learning Representations (ICLR) 2021. arXiv
Kumar, S., Ellis, C.T., O'Connell, T.P., Chun, M.M., Turk-Browne, N.B. (2020) Searching through functional space reveals distributed visual, auditory, and semantic coding in the human brain. PLoS Computational Biology, 16(12) e1008457.
Kumar, S., Yoo, K., Rosenberg, M. D., Scheinost, D., Constable, R. T., Zhang, S., ... & Chun, M. M. (2019). An information network flow approach for measuring functional connectivity and predicting behavior. Brain and behavior, 9(8), e01346.
* indicates equal contribution / co-first authorship.